Abstract
Quality inspection is a critical step in ensuring the quality and efficiency of textile production processes. With the increasing complexity and scale of modern textile manufacturing systems, the need for accurate and efficient quality inspection and defect detection techniques has become paramount. This paper compares supervised and unsupervised Machine Learning techniques for defect detection in the context of industrial textile production, in terms of their respective advantages and disadvantages, and their implementation and computational costs. We explore the use of an autoencoder for the detection of defects in textiles. The goal of this preliminary work is to find out if unsupervised methods can successfully train models with good performance without the need for defect labelled data. (c) 2023 The Authors. Published by Elsevier B.V.

Abstract
Given the new requirements of Machine Learning problems in the last years, especially in what concerns the volume, diversity and speed of data, new approaches are needed to deal with the associated challenges. In this paper we describe CEDEs - a distributed learning system that runs on top of an Hadoop cluster and takes advantage of blocks, replication and balancing. CEDEs trains models in a distributed manner following the principle of data locality, and is able to change parts of the model through an optimization module, thus allowing a model to evolve over time as the data changes. This paper describes its generic architecture, details the implementation of the first modules, and provides a first validation.

Abstract
Artificial Intelligence is a hot topic and Machine Learning is one of the most fluent approaches and practices. The problem with many AI models is that they can be useful for predicting but they are bad at explaining why they behave a certain way. In some contexts, the explanation may even be more important than the prediction itself, mainly in systems in which decisions are made based on their predictions. Therefore, it is increasingly necessary to provide a forecast accompanied by an explanation, when decisions are made automatically. This paper aims to contribute to the solution of problem based on human mobility research, or at least, to be a starting point for its solution.

Abstract
The evaluation is a determining factor in developing successful strategies for learning. In a classroom context, the teacher can observe the behavior of students and identify different ways to facilitate the assessment without inducing stress, avoiding the negative consequences of this on the result of learning. However, in learning environments eLearning direct contact is impossible and, therefore, there should be alternative ways to provide both detection and prevention of stress during the evaluation. It is therefore appropriate stress analysis and identification of strategies for solving problems arising from its appearance. In this work, a stress analysis module for use is proposed for the online student assessment, which is capable of indicating to the teaching moments more propitious time to intervene and the contents that cause greater difficulties. In this way, the teacher can effectively assist students who need it most.

Abstract
In recent years, the development and use of mobile devices such as smartphones and tablets grew significantly. They are used for virtually every activity of our lives, from communication or online shopping to e-banking or gaming, just to name a few. As a consequence, these devices contribute significantly to make our lives more digital, with all the perks and risks that this encompasses. One of the most serious risk is that of an authorized individual gaining physical access to our mobile device and, potentially, to all the applications and personal data it contains. Most of mobile devices are protected using some kind of password, that can be easily spotted by unauthorized users or event guessed. In the last years, new authentication mechanisms have been proposed, such as those using traditional biometrics or behavioral biometrics. In this paper we propose a new continuous authentication mechanism for mobile devices based on behavioral biometrics that monitors user interaction behavior for classifying the identity of the user. © Springer Nature Switzerland AG 2020.

Abstract
In a time in which a significant amount of interpersonal interactions take place online, one must enquire to which extent are these milieus suitable for supporting the complexity of our communication. This is especially important in more sensitive domains, such as the one of Online Dispute Resolution, in which inefficient communication environments may result in misunderstandings, poor decisions or the escalation of the conflict. The conflict manager, in particular, may find his skills severely diminished, namely in what concerns the accurate perception of the state of the parties. In this paper the development of a rich communication framework is detailed that conveys contextual information about their users, harnessed from the transparent analysis of their behaviour while communicating. Using it, the conflict manager may not only better perceive the conflict and how it affects each party but also take better contextualized decisions, closer to the ones taken in face-to-face settings.